OpenEvents V1: Large-Scale Benchmark Dataset for Multimodal Event Grounding
This dataset addresses the need for multimodal AI systems to perform deep reasoning over complex real-world events, though it is incremental as it builds on existing vision-language datasets by focusing on event grounding.
The paper tackles the problem of advancing event-centric vision-language understanding by introducing OpenEvents V1, a large-scale benchmark dataset with over 200,000 news articles and 400,000 images, and provides baseline results for tasks like event-aware captioning and retrieval.
We introduce OpenEvents V1a large-scale benchmark dataset designed to advance event-centric vision-language understanding. Unlike conventional image captioning and retrieval datasets that focus on surface-level descriptions, OpenEvents V1 dataset emphasizes contextual and temporal grounding through three primary tasks: (1) generating rich, event-aware image captions, (2) retrieving event-relevant news articles from image queries, and (3) retrieving event-relevant images from narrative-style textual queries. The dataset comprises over 200,000 news articles and 400,000 associated images sourced from CNN and The Guardian, spanning diverse domains and time periods. We provide extensive baseline results and standardized evaluation protocols for all tasks. OpenEvents V1 establishes a robust foundation for developing multimodal AI systems capable of deep reasoning over complex real-world events. The dataset is publicly available at https://ltnghia.github.io/eventa/openevents-v1.